A comparative analysis of analytic approaches for predicting performance on a putative behavioural marker for Alzheimer's disease
Our analysis highlights the value of integrating machine learning with regression approaches to identify VSTMBT predictors and their role in risk stratification. Machine learning complements regression in population-based AD assessments. Future research should apply these models for individual prediction and early detection.
Authors
- Tamlyn Watermeyer (ORCID: https://orcid.org/0000-0002-8232-5305)
- Samuel Danso (ORCID: https://orcid.org/0000-0002-9396-2107)
- Mario A A Parra
- Dennis Boateng
- Joe Butler
- Binding in Neuropsychiatric Disorders (B.I.N.D) Group
Institutions
- University of Strathclyde (GB)
- Northumbria University (GB)
- Alzheimer Scotland (GB)
- Academic Health Science Network North East and North Cumbria (GB)
- UK Dementia Research Institute (GB)
- Statistical Service (CY)
- University of Sunderland (GB)
- University of Edinburgh (GB)
Publication Details
- Journal
- Alzheimer s & Dementia
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1002/alz70857_106450
- Primary Topic
- Dementia and Cognitive Impairment Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00